metadata

library_name: transformers
language:
  - mr
license: apache-2.0
base_model: openai/whisper-large
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: whisper-large-marathi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 17
          type: mozilla-foundation/common_voice_17_0
          config: mr
          split: test
          args: mr
        metrics:
          - name: Wer
            type: wer
            value: 11.99582494594796

whisper-large-marathi

This model is a fine-tuned version of openai/whisper-large on the Common Voice 17 dataset. It achieves the following results on the evaluation set:

Loss: 0.1845
Wer Ortho: 32.4713
Wer: 11.9958

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 12
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 20
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.1771	1.0	250	0.2041	36.0371	13.7851
0.0806	2.0	500	0.1845	32.4713	11.9958

Framework versions

Transformers 4.44.2
Pytorch 2.5.0+cu121
Datasets 3.1.0
Tokenizers 0.19.1